> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# v1.4.23

> v1.4.23 changelog - 2026-04-18

<Tabs>
  <Tab title="NPX">`bash npx -y @maximhq/bifrost --transport-version v1.4.23 `</Tab>

  <Tab title="Docker">
    `bash docker pull maximhq/bifrost:v1.4.23 docker run -p 8080:8080 maximhq/bifrost:v1.4.23 `
  </Tab>
</Tabs>

<Update label="Bifrost(HTTP)" description="1.4.23">
  ## ✨ Features

  * **Claude Opus 4.7 Support** - Added compatibility for Anthropic's Claude Opus 4.7 model, including adaptive thinking, task-budgets beta header, `display` parameter handling, and "xhigh" effort mapping
  * **Anthropic Structured Outputs** - Added `response_format` and structured output support for Anthropic models across chat completions and Responses API, including JSON-schema and JSON-object formats with order-preserving merge of additional model request fields (thanks [@emirhanmutlu-natuvion](https://github.com/emirhanmutlu-natuvion)!)
  * **MCP Tool Annotations** - Preserve MCP tool annotations (`title`, `readOnly`, `destructive`, `idempotent`, `openWorld`) in bidirectional conversion between MCP tools and Bifrost chat tools so agents can reason about tool behavior
  * **Anthropic Server Tools** - Expanded Anthropic chat schema and Responses converters to surface server-side tools (web search, code execution, computer use containers) end-to-end

  ## 🐞 Fixed

  * **Provider Queue Shutdown Panic** - Eliminated `send on closed channel` panics in provider queue shutdown by leaving queue channels open and exiting workers via the `done` signal; stale producers transparently re-route to new queues during `UpdateProvider`, with rollback on failed updates
  * **OpenAI Tool Result Output** - Flatten array-form `tool_result` output into a newline-joined string before marshaling for the Responses API so strict upstreams (Ollama Cloud, openai-go typed models) no longer reject it with HTTP 400; non-text blocks (images, files) are preserved (thanks [@martingiguere](https://github.com/martingiguere)!)
  * **vLLM Token Usage** - Treat `delta.content=""` the same as `nil` in streaming so the synthesis chunk retains its `finish_reason`, restoring token usage attribution in logs and UI
  * **Config Schema Validator** - Corrected JSON-path lookups for concurrency and SCIM blocks in the schema validation script, and reformatted `transports/config.schema.json` for readability
  * **CI Egress Hardening** - Switched `step-security/harden-runner` from `audit` to `block` across all GitHub Actions workflows with explicit `allowed-endpoints` per job
  * **Gemini Tool Outputs** - Handle content block tool outputs in Responses API path for `function_call_output` messages (thanks [@tom-diacono](https://github.com/tom-diacono)!)
  * **Bedrock Streaming** - Emit `message_stop` event for Anthropic invoke stream and case-insensitive `anthropic-beta` header merging (thanks [@tefimov](https://github.com/tefimov)!)
  * **Bedrock Tool Images** - Preserve image content blocks in tool results when converting Anthropic Messages to Bedrock Converse API (thanks [@Edward-Upton](https://github.com/Edward-Upton)!)
  * **Gemini Thinking Level** - Preserved `thinkingLevel` parameters across round-trip conversions and corrected finish reason mapping
  * **Anthropic WebSearch** - Removed the Claude Code user agent restriction so WebSearch tool arguments flow for all clients
  * **Responses Streaming Errors** - Capture errors mid-stream in the Responses API so transport clients see failures instead of silent termination
  * **Anthropic Request Fallbacks** - Dropped fallback fields from outgoing Anthropic requests to avoid schema validation errors
  * **Async Context Propagation** - Preserve context values in async requests so downstream handlers retain request-scoped data
  * **Custom Providers** - Allow custom providers without a list-models endpoint to accept any model rather than restricting on virtual key registration
  * **OTEL Plugin** - Default `insecure` to `true` in config.json and include fallbacks in emitted OTEL metrics
  * **Payload Marshalling** - Removed unnecessary marshalling of payload in the transport path
  * **Helm mcpClientConfig** - Fixed templating for `mcpClientConfig` (thanks [@crust3780](https://github.com/crust3780)!)
  * **Helm Chart** - Refreshed the helm chart with validation fixes and removed the prerelease tag
</Update>

<Update label="Core" description="1.4.22">
  * fix: OpenAI provider - flatten array-form tool\_result output for Responses API (thanks [@martingiguere](https://github.com/martingiguere)!)
  * fix: Gemini provider - handle content block tool outputs in Responses API path (thanks [@tom-diacono](https://github.com/tom-diacono)!)
  * fix: case-insensitive `anthropic-beta` merge in `MergeBetaHeaders`
  * fix: Bedrock provider - emit message\_stop event for Anthropic invoke stream (thanks [@tefimov](https://github.com/tefimov)!)
  * fix: Bedrock provider - preserve image content in tool results for Converse API (thanks [@Edward-Upton](https://github.com/Edward-Upton)!)
  * fix: gemini preserves thinkingLevel parameters during round-trip and finish reason mapping
  * fix: WebSearch tool argument handling for all clients by removing the Claude Code user agent restriction
  * fix: capture responses streaming API errors
  * fix: delete fallbacks from outgoing Anthropic requests
  * feat: claude-opus-4-7 compatibility
  * fix: token usage for vllm
</Update>

<Update label="Framework" description="1.2.39">
  * chore: upgraded core to v1.4.20
  * fix: preserve context values in async requests
  * fix: capture responses streaming API errors
  * fix: otel plugin fixes
  * fix: allow custom providers without a list models endpoint to register any model
</Update>

<Update label="governance" description="1.4.39">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
  * fix: allow custom providers without a list models endpoint to pass in any model rather than restrict it on vk
</Update>

<Update label="jsonparser" description="1.4.38">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>

<Update label="litellmcompat" description="0.0.28">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>

<Update label="logging" description="1.4.39">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
  * fix: capture responses streaming API errors
</Update>

<Update label="maxim" description="1.5.39">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>

<Update label="mocker" description="1.4.38">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>

<Update label="otel" description="1.1.38">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
  * fix: sets default for `insecure` to `true` for config.json
  * fix: includes fallbacks in otel metrics
</Update>

<Update label="semanticcache" description="1.4.37">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>

<Update label="telemetry" description="1.4.39">
  * chore: upgraded core to v1.4.20 and framework to v1.2.39
</Update>